Predicting Long-Term Allograft Survival in Liver Transplant Recipients

TL;DR

This paper introduces MAS, a simple linear risk score for predicting long-term liver allograft failure, demonstrating its superior performance and robustness over complex models across diverse patient populations.

Contribution

The paper presents MAS, a novel, interpretable linear risk score that outperforms complex models in predicting liver transplant failure and assesses model robustness across different data distributions.

Findings

MAS outperforms advanced survival models in accuracy.

Complex models are more vulnerable to distribution shifts.

Routine ML validation may be insufficient for clinical deployment.

Abstract

Liver allograft failure occurs in approximately 20% of liver transplant recipients within five years post-transplant, leading to mortality or the need for retransplantation. Providing an accurate and interpretable model for individualized risk estimation of graft failure is essential for improving post-transplant care. To this end, we introduce the Model for Allograft Survival (MAS), a simple linear risk score that outperforms other advanced survival models. Using longitudinal patient follow-up data from the United States (U.S.), we develop our models on 82,959 liver transplant recipients and conduct multi-site evaluations on 11 regions. Additionally, by testing on a separate non-U.S. cohort, we explore the out-of-distribution generalization performance of various models without additional fine-tuning, a crucial property for clinical deployment. We find that the most complex models are also the ones most vulnerable to distribution shifts despite achieving the best in-distribution performance. Our findings not only provide a strong risk score for predicting long-term graft failure but also suggest that the routine machine learning pipeline with only in-distribution held-out validation could create harmful consequences for patients at deployment.